Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 361
• Descripción:
• Frecuencia: mes
• Variables: tmax, tmin, precip
• Dimensiones del mapa: 5,5
• Iteraciones: 1000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-361.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.214.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
 901 4369 6277 6830 5376  528 2168 3800 5861 6738 2442 4149 5627 5782 6624  463 
  17   18   19   20   21   22   23   24   25 
1060 3111 5165 4635   59 1116 2114 3322 6364 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("tmax", "tmin", "precip")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

          tmax      tmin     precip
[1,] 0.7501526 0.7047923 -0.7143514
[2,] 0.5717444 0.7352300  0.2673274

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

     tmax    precip      tmin 
0.9701458 0.9663628 0.9631780 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 2.000   1st Qu.:113.0   1st Qu.:  21.00   1st Qu.:  6.00  
 Median : 4.000   Median :143.0   Median :  48.00   Median : 17.00  
 Mean   : 5.816   Mean   :139.2   Mean   :  45.91   Mean   : 24.08  
 3rd Qu.:11.000   3rd Qu.:168.0   3rd Qu.:  71.00   3rd Qu.: 35.00  
 Max.   :12.000   Max.   :336.0   Max.   : 219.00   Max.   :174.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:40.07   1st Qu.: -5.3456  
 Median :0.000000   Median :   0.000   Median :41.42   Median : -2.9056  
 Mean   :0.000654   Mean   :   1.009   Mean   :40.77   Mean   : -2.8506  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.44   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  85.0  
 Median : 445.0  
 Mean   : 561.3  
 3rd Qu.: 785.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 41.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 5.000   1st Qu.:214.0   1st Qu.:110.0   1st Qu.: 1.000   1st Qu.:0  
 Median : 7.000   Median :248.0   Median :142.0   Median : 7.000   Median :0  
 Mean   : 7.057   Mean   :250.5   Mean   :142.5   Mean   : 9.563   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:285.0   3rd Qu.:172.0   3rd Qu.:15.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :62.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8728   1st Qu.:  32.0  
 Median : 0.00000   Median :39.95   Median : -3.6325   Median :  87.0  
 Mean   : 0.00935   Mean   :38.75   Mean   : -3.9125   Mean   : 300.9  
 3rd Qu.: 0.00000   3rd Qu.:41.65   3rd Qu.:  0.4731   3rd Qu.: 541.0  
 Max.   :38.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :175.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:116.0   1st Qu.: 63.00   1st Qu.:186.0   1st Qu.:0  
 Median : 8.000   Median :136.0   Median : 80.00   Median :206.0   Median :0  
 Mean   : 6.763   Mean   :153.0   Mean   : 86.95   Mean   :221.1   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:159.5   3rd Qu.: 99.00   3rd Qu.:232.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve        longitud        latitud           altitud       
 Min.   :  0.00   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.00   1st Qu.:40.72   1st Qu.: -8.624   1st Qu.:  86.55  
 Median :  0.00   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   : 10.34   Mean   :40.71   Mean   : -7.114   Mean   : 416.47  
 3rd Qu.:  0.00   3rd Qu.:42.89   3rd Qu.: -5.600   3rd Qu.: 370.00  
 Max.   :607.00   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 2.000   1st Qu.:112.0   1st Qu.:  19.00   1st Qu.:  6.00  
 Median : 4.000   Median :142.0   Median :  45.00   Median : 15.00  
 Mean   : 5.688   Mean   :137.2   Mean   :  42.63   Mean   : 19.97  
 3rd Qu.:11.000   3rd Qu.:166.0   3rd Qu.:  67.00   3rd Qu.: 31.00  
 Max.   :12.000   Max.   :263.0   Max.   : 159.00   Max.   :126.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:40.07   1st Qu.: -4.8500  
 Median :0.000000   Median :   0.000   Median :41.42   Median : -2.7331  
 Mean   :0.000696   Mean   :   1.036   Mean   :40.74   Mean   : -2.7452  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.38   3rd Qu.:  0.5356  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  90.0  
 Median : 513.0  
 Mean   : 581.6  
 3rd Qu.: 790.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 41.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 5.000   1st Qu.:214.0   1st Qu.:110.0   1st Qu.: 1.000   1st Qu.:0  
 Median : 7.000   Median :248.0   Median :142.0   Median : 7.000   Median :0  
 Mean   : 7.057   Mean   :250.5   Mean   :142.5   Mean   : 9.563   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:285.0   3rd Qu.:172.0   3rd Qu.:15.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :62.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8728   1st Qu.:  32.0  
 Median : 0.00000   Median :39.95   Median : -3.6325   Median :  87.0  
 Mean   : 0.00935   Mean   :38.75   Mean   : -3.9125   Mean   : 300.9  
 3rd Qu.: 0.00000   3rd Qu.:41.65   3rd Qu.:  0.4731   3rd Qu.: 541.0  
 Max.   :38.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   : 53.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.:133.0   1st Qu.: 67.00   1st Qu.: 70.00   1st Qu.:0  
 Median :10.000   Median :169.0   Median : 97.00   Median : 81.00   Median :0  
 Mean   : 7.776   Mean   :169.3   Mean   : 95.84   Mean   : 86.77   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:203.0   3rd Qu.:125.00   3rd Qu.: 98.00   3rd Qu.:0  
 Max.   :12.000   Max.   :336.0   Max.   :219.00   Max.   :174.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:40.78   1st Qu.: -8.411   1st Qu.:  27.1  
 Median :  0.0000   Median :42.43   Median : -4.049   Median :  98.0  
 Mean   :  0.5991   Mean   :41.13   Mean   : -4.455   Mean   : 250.9  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -1.787   3rd Qu.: 261.0  
 Max.   :892.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :175.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:116.0   1st Qu.: 63.00   1st Qu.:186.0   1st Qu.:0  
 Median : 8.000   Median :136.0   Median : 80.00   Median :206.0   Median :0  
 Mean   : 6.763   Mean   :153.0   Mean   : 86.95   Mean   :221.1   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:159.5   3rd Qu.: 99.00   3rd Qu.:232.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve        longitud        latitud           altitud       
 Min.   :  0.00   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.00   1st Qu.:40.72   1st Qu.: -8.624   1st Qu.:  86.55  
 Median :  0.00   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   : 10.34   Mean   :40.71   Mean   : -7.114   Mean   : 416.47  
 3rd Qu.:  0.00   3rd Qu.:42.89   3rd Qu.: -5.600   3rd Qu.: 370.00  
 Max.   :607.00   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.:  11.00   1st Qu.: 4.00  
 Median : 3.000   Median :138.0   Median :  36.00   Median : 9.00  
 Mean   : 5.421   Mean   :132.8   Mean   :  32.14   Mean   :10.34  
 3rd Qu.:11.000   3rd Qu.:162.0   3rd Qu.:  57.00   3rd Qu.:16.00  
 Max.   :12.000   Max.   :250.0   Max.   : 105.00   Max.   :45.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:39.95   1st Qu.: -4.5353  
 Median :0.000000   Median :   0.0000   Median :41.11   Median : -2.3308  
 Mean   :0.001007   Mean   :   0.6689   Mean   :40.54   Mean   : -2.4561  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:41.98   3rd Qu.:  0.5831  
 Max.   :6.000000   Max.   :1494.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.: 143.0  
 Median : 582.0  
 Mean   : 618.9  
 3rd Qu.: 846.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 41.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 5.000   1st Qu.:214.0   1st Qu.:110.0   1st Qu.: 1.000   1st Qu.:0  
 Median : 7.000   Median :248.0   Median :142.0   Median : 7.000   Median :0  
 Mean   : 7.057   Mean   :250.5   Mean   :142.5   Mean   : 9.563   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:285.0   3rd Qu.:172.0   3rd Qu.:15.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :62.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8728   1st Qu.:  32.0  
 Median : 0.00000   Median :39.95   Median : -3.6325   Median :  87.0  
 Mean   : 0.00935   Mean   :38.75   Mean   : -3.9125   Mean   : 300.9  
 3rd Qu.: 0.00000   3rd Qu.:41.65   3rd Qu.:  0.4731   3rd Qu.: 541.0  
 Max.   :38.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-47.0   Min.   :-115.00   Min.   : 23.00  
 1st Qu.: 3.000   1st Qu.:125.0   1st Qu.:  46.00   1st Qu.: 32.00  
 Median : 5.000   Median :151.0   Median :  69.00   Median : 39.00  
 Mean   : 6.285   Mean   :147.2   Mean   :  66.14   Mean   : 41.55  
 3rd Qu.:11.000   3rd Qu.:176.0   3rd Qu.:  91.00   3rd Qu.: 48.00  
 Max.   :12.000   Max.   :263.0   Max.   : 159.00   Max.   :126.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:40.63   1st Qu.: -5.8728  
 Median :0   Median :   0.000   Median :42.24   Median : -3.7892  
 Mean   :0   Mean   :   1.858   Mean   :41.20   Mean   : -3.3937  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:43.30   3rd Qu.:  0.3664  
 Max.   :0   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud    
 Min.   :   1  
 1st Qu.:  58  
 Median : 251  
 Mean   : 498  
 3rd Qu.: 632  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   : 53.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.:133.0   1st Qu.: 67.00   1st Qu.: 70.00   1st Qu.:0  
 Median :10.000   Median :169.0   Median : 97.00   Median : 81.00   Median :0  
 Mean   : 7.776   Mean   :169.3   Mean   : 95.84   Mean   : 86.77   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:203.0   3rd Qu.:125.00   3rd Qu.: 98.00   3rd Qu.:0  
 Max.   :12.000   Max.   :336.0   Max.   :219.00   Max.   :174.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:40.78   1st Qu.: -8.411   1st Qu.:  27.1  
 Median :  0.0000   Median :42.43   Median : -4.049   Median :  98.0  
 Mean   :  0.5991   Mean   :41.13   Mean   : -4.455   Mean   : 250.9  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -1.787   3rd Qu.: 261.0  
 Max.   :892.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :175.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:116.0   1st Qu.: 63.00   1st Qu.:186.0   1st Qu.:0  
 Median : 8.000   Median :136.0   Median : 80.00   Median :206.0   Median :0  
 Mean   : 6.763   Mean   :153.0   Mean   : 86.95   Mean   :221.1   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:159.5   3rd Qu.: 99.00   3rd Qu.:232.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve        longitud        latitud           altitud       
 Min.   :  0.00   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.00   1st Qu.:40.72   1st Qu.: -8.624   1st Qu.:  86.55  
 Median :  0.00   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   : 10.34   Mean   :40.71   Mean   : -7.114   Mean   : 416.47  
 3rd Qu.:  0.00   3rd Qu.:42.89   3rd Qu.: -5.600   3rd Qu.: 370.00  
 Max.   :607.00   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.:  11.00   1st Qu.: 4.00  
 Median : 3.000   Median :138.0   Median :  36.00   Median : 9.00  
 Mean   : 5.421   Mean   :132.8   Mean   :  32.14   Mean   :10.34  
 3rd Qu.:11.000   3rd Qu.:162.0   3rd Qu.:  57.00   3rd Qu.:16.00  
 Max.   :12.000   Max.   :250.0   Max.   : 105.00   Max.   :45.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:39.95   1st Qu.: -4.5353  
 Median :0.000000   Median :   0.0000   Median :41.11   Median : -2.3308  
 Mean   :0.001007   Mean   :   0.6689   Mean   :40.54   Mean   : -2.4561  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:41.98   3rd Qu.:  0.5831  
 Max.   :6.000000   Max.   :1494.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.: 143.0  
 Median : 582.0  
 Mean   : 618.9  
 3rd Qu.: 846.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip         nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 41.0   Min.   : 0.0   Min.   :0  
 1st Qu.: 5.000   1st Qu.:200.0   1st Qu.: 97.0   1st Qu.: 4.0   1st Qu.:0  
 Median : 6.000   Median :222.0   Median :118.0   Median :10.0   Median :0  
 Mean   : 6.746   Mean   :221.4   Mean   :120.5   Mean   :12.3   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:243.0   3rd Qu.:143.0   3rd Qu.:19.0   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :220.0   Max.   :62.0   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -6.0442   1st Qu.:  32.0  
 Median : 0.00000   Median :40.47   Median : -3.7642   Median :  90.0  
 Mean   : 0.01518   Mean   :38.92   Mean   : -4.2110   Mean   : 325.3  
 3rd Qu.: 0.00000   3rd Qu.:42.05   3rd Qu.:  0.3664   3rd Qu.: 567.0  
 Max.   :38.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-47.0   Min.   :-115.00   Min.   : 23.00  
 1st Qu.: 3.000   1st Qu.:125.0   1st Qu.:  46.00   1st Qu.: 32.00  
 Median : 5.000   Median :151.0   Median :  69.00   Median : 39.00  
 Mean   : 6.285   Mean   :147.2   Mean   :  66.14   Mean   : 41.55  
 3rd Qu.:11.000   3rd Qu.:176.0   3rd Qu.:  91.00   3rd Qu.: 48.00  
 Max.   :12.000   Max.   :263.0   Max.   : 159.00   Max.   :126.00  
     nevada    prof_nieve          longitud        latitud        
 Min.   :0   Min.   :   0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:40.63   1st Qu.: -5.8728  
 Median :0   Median :   0.000   Median :42.24   Median : -3.7892  
 Mean   :0   Mean   :   1.858   Mean   :41.20   Mean   : -3.3937  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:43.30   3rd Qu.:  0.3664  
 Max.   :0   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud    
 Min.   :   1  
 1st Qu.:  58  
 Median : 251  
 Mean   : 498  
 3rd Qu.: 632  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 2.00   Min.   :228.0   Min.   : 96.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.00   1st Qu.:276.0   1st Qu.:156.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.00   Median :294.0   Median :179.0   Median : 2.000   Median :0  
 Mean   : 7.55   Mean   :296.7   Mean   :177.3   Mean   : 5.225   Mean   :0  
 3rd Qu.: 8.00   3rd Qu.:315.0   3rd Qu.:198.0   3rd Qu.: 8.000   3rd Qu.:0  
 Max.   :12.00   Max.   :403.0   Max.   :254.0   Max.   :37.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :0.00e+00   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:37.26   1st Qu.: -5.6156   1st Qu.:  32.0  
 Median :0.00e+00   Median :39.49   Median : -2.9553   Median :  87.0  
 Mean   :9.95e-05   Mean   :38.49   Mean   : -3.4392   Mean   : 262.2  
 3rd Qu.:0.00e+00   3rd Qu.:41.15   3rd Qu.:  0.4942   3rd Qu.: 540.0  
 Max.   :2.00e+00   Max.   :43.56   Max.   :  4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   : 53.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.:133.0   1st Qu.: 67.00   1st Qu.: 70.00   1st Qu.:0  
 Median :10.000   Median :169.0   Median : 97.00   Median : 81.00   Median :0  
 Mean   : 7.776   Mean   :169.3   Mean   : 95.84   Mean   : 86.77   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:203.0   3rd Qu.:125.00   3rd Qu.: 98.00   3rd Qu.:0  
 Max.   :12.000   Max.   :336.0   Max.   :219.00   Max.   :174.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:40.78   1st Qu.: -8.411   1st Qu.:  27.1  
 Median :  0.0000   Median :42.43   Median : -4.049   Median :  98.0  
 Mean   :  0.5991   Mean   :41.13   Mean   : -4.455   Mean   : 250.9  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -1.787   3rd Qu.: 261.0  
 Max.   :892.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :175.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:116.0   1st Qu.: 63.00   1st Qu.:186.0   1st Qu.:0  
 Median : 8.000   Median :136.0   Median : 80.00   Median :206.0   Median :0  
 Mean   : 6.763   Mean   :153.0   Mean   : 86.95   Mean   :221.1   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:159.5   3rd Qu.: 99.00   3rd Qu.:232.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve        longitud        latitud           altitud       
 Min.   :  0.00   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.00   1st Qu.:40.72   1st Qu.: -8.624   1st Qu.:  86.55  
 Median :  0.00   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   : 10.34   Mean   :40.71   Mean   : -7.114   Mean   : 416.47  
 3rd Qu.:  0.00   3rd Qu.:42.89   3rd Qu.: -5.600   3rd Qu.: 370.00  
 Max.   :607.00   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.:  11.00   1st Qu.: 4.00  
 Median : 3.000   Median :138.0   Median :  36.00   Median : 9.00  
 Mean   : 5.421   Mean   :132.8   Mean   :  32.14   Mean   :10.34  
 3rd Qu.:11.000   3rd Qu.:162.0   3rd Qu.:  57.00   3rd Qu.:16.00  
 Max.   :12.000   Max.   :250.0   Max.   : 105.00   Max.   :45.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:39.95   1st Qu.: -4.5353  
 Median :0.000000   Median :   0.0000   Median :41.11   Median : -2.3308  
 Mean   :0.001007   Mean   :   0.6689   Mean   :40.54   Mean   : -2.4561  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:41.98   3rd Qu.:  0.5831  
 Max.   :6.000000   Max.   :1494.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.: 143.0  
 Median : 582.0  
 Mean   : 618.9  
 3rd Qu.: 846.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip         nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 41.0   Min.   : 0.0   Min.   :0  
 1st Qu.: 5.000   1st Qu.:200.0   1st Qu.: 97.0   1st Qu.: 4.0   1st Qu.:0  
 Median : 6.000   Median :222.0   Median :118.0   Median :10.0   Median :0  
 Mean   : 6.746   Mean   :221.4   Mean   :120.5   Mean   :12.3   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:243.0   3rd Qu.:143.0   3rd Qu.:19.0   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :220.0   Max.   :62.0   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -6.0442   1st Qu.:  32.0  
 Median : 0.00000   Median :40.47   Median : -3.7642   Median :  90.0  
 Mean   : 0.01518   Mean   :38.92   Mean   : -4.2110   Mean   : 325.3  
 3rd Qu.: 0.00000   3rd Qu.:42.05   3rd Qu.:  0.3664   3rd Qu.: 567.0  
 Max.   :38.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-47.00   Min.   :-115.00   Min.   : 45.00  
 1st Qu.: 2.000   1st Qu.:  8.00   1st Qu.: -49.00   1st Qu.: 54.00  
 Median : 4.000   Median : 30.00   Median : -27.50   Median : 62.00  
 Mean   : 5.712   Mean   : 29.34   Mean   : -30.13   Mean   : 65.66  
 3rd Qu.:11.000   3rd Qu.: 51.00   3rd Qu.:  -8.00   3rd Qu.: 75.00  
 Max.   :12.000   Max.   :104.00   Max.   :  24.00   Max.   :126.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.: -4.0103  
 Median :0   Median :   0.00   Median :42.47   Median :  0.7789  
 Mean   :0   Mean   :  36.55   Mean   :41.53   Mean   : -1.1603  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.:  1.2717  
 Max.   :0   Max.   :1834.00   Max.   :43.31   Max.   :  2.4378  
    altitud    
 Min.   :  42  
 1st Qu.:1894  
 Median :2230  
 Mean   :2083  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 46.0   Min.   :-39.00   Min.   :23.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:129.0   1st Qu.: 50.00   1st Qu.:32.00   1st Qu.:0  
 Median : 5.000   Median :152.0   Median : 71.00   Median :38.00   Median :0  
 Mean   : 6.311   Mean   :152.4   Mean   : 70.42   Mean   :40.47   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:177.0   3rd Qu.: 92.00   3rd Qu.:47.00   3rd Qu.:0  
 Max.   :12.000   Max.   :263.0   Max.   :159.00   Max.   :71.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:40.47   1st Qu.: -5.8792   1st Qu.:  52.0  
 Median :  0.0000   Median :42.24   Median : -3.7892   Median : 251.0  
 Mean   :  0.3143   Mean   :41.19   Mean   : -3.4930   Mean   : 427.5  
 3rd Qu.:  0.0000   3rd Qu.:43.30   3rd Qu.:  0.0714   3rd Qu.: 609.0  
 Max.   :666.0000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 2.00   Min.   :228.0   Min.   : 96.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.00   1st Qu.:276.0   1st Qu.:156.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.00   Median :294.0   Median :179.0   Median : 2.000   Median :0  
 Mean   : 7.55   Mean   :296.7   Mean   :177.3   Mean   : 5.225   Mean   :0  
 3rd Qu.: 8.00   3rd Qu.:315.0   3rd Qu.:198.0   3rd Qu.: 8.000   3rd Qu.:0  
 Max.   :12.00   Max.   :403.0   Max.   :254.0   Max.   :37.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :0.00e+00   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:37.26   1st Qu.: -5.6156   1st Qu.:  32.0  
 Median :0.00e+00   Median :39.49   Median : -2.9553   Median :  87.0  
 Mean   :9.95e-05   Mean   :38.49   Mean   : -3.4392   Mean   : 262.2  
 3rd Qu.:0.00e+00   3rd Qu.:41.15   3rd Qu.:  0.4942   3rd Qu.: 540.0  
 Max.   :2.00e+00   Max.   :43.56   Max.   :  4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax          tmin           precip          nevada 
 Min.   : 1.000   Min.   : -8   Min.   :-58.0   Min.   :106.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:119   1st Qu.: 57.0   1st Qu.:114.0   1st Qu.:0  
 Median :10.000   Median :140   Median : 78.0   Median :124.0   Median :0  
 Mean   : 7.803   Mean   :144   Mean   : 77.9   Mean   :128.1   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:169   3rd Qu.:103.0   3rd Qu.:138.5   3rd Qu.:0  
 Max.   :12.000   Max.   :326   Max.   :207.0   Max.   :174.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.29   1st Qu.: -8.616   1st Qu.:  32.0  
 Median :  0.000   Median :42.43   Median : -6.949   Median : 251.0  
 Mean   :  2.821   Mean   :41.40   Mean   : -5.700   Mean   : 365.6  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -2.039   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  3.035   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 1.00   Min.   : 49.0   Min.   :-22.00   Min.   : 53.00   Min.   :0  
 1st Qu.: 4.00   1st Qu.:138.8   1st Qu.: 71.00   1st Qu.: 67.00   1st Qu.:0  
 Median :10.00   Median :176.0   Median :103.00   Median : 77.00   Median :0  
 Mean   : 7.77   Mean   :174.7   Mean   : 99.65   Mean   : 77.98   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:208.0   3rd Qu.:128.00   3rd Qu.: 88.00   3rd Qu.:0  
 Max.   :12.00   Max.   :336.0   Max.   :219.00   Max.   :118.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   : 0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.: 0.0000   1st Qu.:39.99   1st Qu.: -8.372   1st Qu.:  27.1  
 Median : 0.0000   Median :42.38   Median : -3.831   Median :  90.5  
 Mean   : 0.1264   Mean   :41.07   Mean   : -4.191   Mean   : 226.5  
 3rd Qu.: 0.0000   3rd Qu.:43.31   3rd Qu.: -1.787   3rd Qu.: 261.0  
 Max.   :45.0000   Max.   :43.57   Max.   :  4.216   Max.   :2519.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :175.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:116.0   1st Qu.: 63.00   1st Qu.:186.0   1st Qu.:0  
 Median : 8.000   Median :136.0   Median : 80.00   Median :206.0   Median :0  
 Mean   : 6.763   Mean   :153.0   Mean   : 86.95   Mean   :221.1   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:159.5   3rd Qu.: 99.00   3rd Qu.:232.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve        longitud        latitud           altitud       
 Min.   :  0.00   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.00   1st Qu.:40.72   1st Qu.: -8.624   1st Qu.:  86.55  
 Median :  0.00   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   : 10.34   Mean   :40.71   Mean   : -7.114   Mean   : 416.47  
 3rd Qu.:  0.00   3rd Qu.:42.89   3rd Qu.: -5.600   3rd Qu.: 370.00  
 Max.   :607.00   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax             tmin               precip     
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.0000   Min.   : 0.00  
 1st Qu.: 1.000   1st Qu.: 76.00   1st Qu.: -15.0000   1st Qu.: 6.00  
 Median : 2.000   Median : 94.00   Median :   3.0000   Median :13.00  
 Mean   : 5.359   Mean   : 89.35   Mean   :   0.5038   Mean   :13.74  
 3rd Qu.:12.000   3rd Qu.:108.00   3rd Qu.:  19.0000   3rd Qu.:21.00  
 Max.   :12.000   Max.   :173.00   Max.   :  60.0000   Max.   :45.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:40.66   1st Qu.: -4.1269  
 Median :0.000000   Median :   0.000   Median :41.59   Median : -2.6544  
 Mean   :0.002426   Mean   :   1.911   Mean   :41.00   Mean   : -2.6947  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.36   3rd Qu.:  0.3264  
 Max.   :6.000000   Max.   :1494.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   2.0  
 1st Qu.: 609.0  
 Median : 790.0  
 Mean   : 938.1  
 3rd Qu.:1056.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin            precip      
 Min.   : 1.000   Min.   : 74.0   Min.   :-40.00   Min.   : 0.000  
 1st Qu.: 2.000   1st Qu.:137.0   1st Qu.: 33.00   1st Qu.: 3.000  
 Median : 3.000   Median :154.0   Median : 49.00   Median : 8.000  
 Mean   : 5.451   Mean   :153.8   Mean   : 47.46   Mean   : 8.696  
 3rd Qu.:11.000   3rd Qu.:171.0   3rd Qu.: 64.00   3rd Qu.:13.000  
 Max.   :12.000   Max.   :250.0   Max.   :105.00   Max.   :28.000  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :28.31   Min.   :-16.499  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:39.47   1st Qu.: -4.535  
 Median :0.0000000   Median : 0.00000   Median :40.95   Median : -1.885  
 Mean   :0.0003203   Mean   : 0.06726   Mean   :40.31   Mean   : -2.341  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.74   3rd Qu.:  0.595  
 Max.   :2.0000000   Max.   :65.00000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  71.0  
 Median : 405.0  
 Mean   : 464.4  
 3rd Qu.: 687.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 41.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.:199.0   1st Qu.: 96.0   1st Qu.: 3.00   1st Qu.:0  
 Median : 6.000   Median :220.0   Median :116.0   Median : 9.00   Median :0  
 Mean   : 6.649   Mean   :219.7   Mean   :118.4   Mean   :10.48   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:241.0   3rd Qu.:139.0   3rd Qu.:17.00   3rd Qu.:0  
 Max.   :12.000   Max.   :309.0   Max.   :201.0   Max.   :31.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud    
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1  
 1st Qu.: 0.00000   1st Qu.:37.18   1st Qu.: -6.0556   1st Qu.:  32  
 Median : 0.00000   Median :40.38   Median : -3.7892   Median :  90  
 Mean   : 0.01498   Mean   :38.82   Mean   : -4.3413   Mean   : 334  
 3rd Qu.: 0.00000   3rd Qu.:41.98   3rd Qu.:  0.0714   3rd Qu.: 609  
 Max.   :38.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-47.00   Min.   :-115.00   Min.   : 45.00  
 1st Qu.: 2.000   1st Qu.:  8.00   1st Qu.: -49.00   1st Qu.: 54.00  
 Median : 4.000   Median : 30.00   Median : -27.50   Median : 62.00  
 Mean   : 5.712   Mean   : 29.34   Mean   : -30.13   Mean   : 65.66  
 3rd Qu.:11.000   3rd Qu.: 51.00   3rd Qu.:  -8.00   3rd Qu.: 75.00  
 Max.   :12.000   Max.   :104.00   Max.   :  24.00   Max.   :126.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.: -4.0103  
 Median :0   Median :   0.00   Median :42.47   Median :  0.7789  
 Mean   :0   Mean   :  36.55   Mean   :41.53   Mean   : -1.1603  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.:  1.2717  
 Max.   :0   Max.   :1834.00   Max.   :43.31   Max.   :  2.4378  
    altitud    
 Min.   :  42  
 1st Qu.:1894  
 Median :2230  
 Mean   :2083  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 46.0   Min.   :-39.00   Min.   :23.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:129.0   1st Qu.: 50.00   1st Qu.:32.00   1st Qu.:0  
 Median : 5.000   Median :152.0   Median : 71.00   Median :38.00   Median :0  
 Mean   : 6.311   Mean   :152.4   Mean   : 70.42   Mean   :40.47   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:177.0   3rd Qu.: 92.00   3rd Qu.:47.00   3rd Qu.:0  
 Max.   :12.000   Max.   :263.0   Max.   :159.00   Max.   :71.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:40.47   1st Qu.: -5.8792   1st Qu.:  52.0  
 Median :  0.0000   Median :42.24   Median : -3.7892   Median : 251.0  
 Mean   :  0.3143   Mean   :41.19   Mean   : -3.4930   Mean   : 427.5  
 3rd Qu.:  0.0000   3rd Qu.:43.30   3rd Qu.:  0.0714   3rd Qu.: 609.0  
 Max.   :666.0000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 2.00   Min.   :228.0   Min.   : 96.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.00   1st Qu.:276.0   1st Qu.:156.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.00   Median :294.0   Median :179.0   Median : 2.000   Median :0  
 Mean   : 7.55   Mean   :296.7   Mean   :177.3   Mean   : 5.225   Mean   :0  
 3rd Qu.: 8.00   3rd Qu.:315.0   3rd Qu.:198.0   3rd Qu.: 8.000   3rd Qu.:0  
 Max.   :12.00   Max.   :403.0   Max.   :254.0   Max.   :37.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :0.00e+00   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:0.00e+00   1st Qu.:37.26   1st Qu.: -5.6156   1st Qu.:  32.0  
 Median :0.00e+00   Median :39.49   Median : -2.9553   Median :  87.0  
 Mean   :9.95e-05   Mean   :38.49   Mean   : -3.4392   Mean   : 262.2  
 3rd Qu.:0.00e+00   3rd Qu.:41.15   3rd Qu.:  0.4942   3rd Qu.: 540.0  
 Max.   :2.00e+00   Max.   :43.56   Max.   :  4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax          tmin           precip          nevada 
 Min.   : 1.000   Min.   : -8   Min.   :-58.0   Min.   :106.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:119   1st Qu.: 57.0   1st Qu.:114.0   1st Qu.:0  
 Median :10.000   Median :140   Median : 78.0   Median :124.0   Median :0  
 Mean   : 7.803   Mean   :144   Mean   : 77.9   Mean   :128.1   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:169   3rd Qu.:103.0   3rd Qu.:138.5   3rd Qu.:0  
 Max.   :12.000   Max.   :326   Max.   :207.0   Max.   :174.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.29   1st Qu.: -8.616   1st Qu.:  32.0  
 Median :  0.000   Median :42.43   Median : -6.949   Median : 251.0  
 Mean   :  2.821   Mean   :41.40   Mean   : -5.700   Mean   : 365.6  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -2.039   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  3.035   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 1.00   Min.   : 49.0   Min.   :-22.00   Min.   : 53.00   Min.   :0  
 1st Qu.: 4.00   1st Qu.:138.8   1st Qu.: 71.00   1st Qu.: 67.00   1st Qu.:0  
 Median :10.00   Median :176.0   Median :103.00   Median : 77.00   Median :0  
 Mean   : 7.77   Mean   :174.7   Mean   : 99.65   Mean   : 77.98   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:208.0   3rd Qu.:128.00   3rd Qu.: 88.00   3rd Qu.:0  
 Max.   :12.00   Max.   :336.0   Max.   :219.00   Max.   :118.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   : 0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.: 0.0000   1st Qu.:39.99   1st Qu.: -8.372   1st Qu.:  27.1  
 Median : 0.0000   Median :42.38   Median : -3.831   Median :  90.5  
 Mean   : 0.1264   Mean   :41.07   Mean   : -4.191   Mean   : 226.5  
 3rd Qu.: 0.0000   3rd Qu.:43.31   3rd Qu.: -1.787   3rd Qu.: 261.0  
 Max.   :45.0000   Max.   :43.57   Max.   :  4.216   Max.   :2519.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :175.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:116.0   1st Qu.: 63.00   1st Qu.:186.0   1st Qu.:0  
 Median : 8.000   Median :136.0   Median : 80.00   Median :206.0   Median :0  
 Mean   : 6.763   Mean   :153.0   Mean   : 86.95   Mean   :221.1   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:159.5   3rd Qu.: 99.00   3rd Qu.:232.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve        longitud        latitud           altitud       
 Min.   :  0.00   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.00   1st Qu.:40.72   1st Qu.: -8.624   1st Qu.:  86.55  
 Median :  0.00   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   : 10.34   Mean   :40.71   Mean   : -7.114   Mean   : 416.47  
 3rd Qu.:  0.00   3rd Qu.:42.89   3rd Qu.: -5.600   3rd Qu.: 370.00  
 Max.   :607.00   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 1.000   Min.   :196.0   Min.   : 90.0   Min.   :26.00   Min.   :0  
 1st Qu.: 7.000   1st Qu.:228.0   1st Qu.:137.0   1st Qu.:32.00   1st Qu.:0  
 Median : 9.000   Median :244.0   Median :150.0   Median :36.00   Median :0  
 Mean   : 8.119   Mean   :245.9   Mean   :151.3   Mean   :37.84   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:263.0   3rd Qu.:165.0   3rd Qu.:42.00   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :220.0   Max.   :62.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:39.48   1st Qu.: -5.598   1st Qu.:  27.0  
 Median : 0.00000   Median :41.52   Median : -1.787   Median :  75.5  
 Mean   : 0.01798   Mean   :40.42   Mean   : -2.376   Mean   : 203.4  
 3rd Qu.: 0.00000   3rd Qu.:42.78   3rd Qu.:  1.397   3rd Qu.: 258.0  
 Max.   :27.00000   Max.   :43.57   Max.   :  4.216   Max.   :1894.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)